AI Layered Process Extraction for RPA Workflow Discovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robotic process automation (RPA) techniques lack an effective mechanism for analyzing data to identify processes that can benefit from automation, limiting their ability to improve or facilitate RPA.
Innovation Solution
Implementing an AI layer-based process extraction method that retrieves data from listeners, processes it through multiple AI layers, and generates RPA workflows when a potential process exceeds a confidence threshold, thereby automating the identification and execution of suitable RPA processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional RPA data collection methods are used, then data can be gathered from business computing systems, but the data cannot be effectively analyzed to identify automatable processes
Solution Approach 1:
The patent segments the data analysis process into multiple AI layers, each performing specific functions: event sequence extraction, pattern recognition, and process identification. This segmentation enables effective process identification from collected data without requiring a single complex analysis mechanism.
Solution Approach 2:
The patent introduces AI models as intermediary components between data collection and process identification. These AI layers act as mediators that transform raw collected data into actionable process insights, bridging the gap between data gathering and automation opportunity identification.
2Measurement precision
If multiple AI layers are implemented to analyze data, then process identification accuracy improves, but system complexity increases
Solution Approach 1:
The analysis system is divided into distinct AI layers with specialized functions. Each layer processes specific aspects of the data (event sequences, patterns, relationships), improving identification accuracy while managing complexity through functional decomposition rather than a monolithic complex system.
Solution Approach 2:
The AI layers are configured dynamically based on the specific automation opportunities being analyzed. The system can adjust which AI layers are activated and their processing depth based on data characteristics, allowing high accuracy when needed while reducing complexity for simpler analysis tasks.
Data Source
AI summary
Artificial intelligence (AI) layer-based process extraction for robotic process automation (RPA) is disclosed. Data collected by RPA robots and/or other sources may be analyzed to identify patterns that can be used to suggest or automatically generate RPA workflows. These AI layers may be used to recognize patterns of user or business system processes contained therein. Each AI layer may “sense” different characteristics in the data and be used individually or in concert with other AI layers to suggest RPA workflows.